Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    XML or HTML tags and structural elements in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    `<start_of_turn> user`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحره
    -0.55
     Collie
    -0.48
     ganger
    -0.48
    -0.47
     halı
    -0.47
     worshi
    -0.46
    Aholisi
    -0.46
     decl
    -0.45
     Hebrew
    -0.45
    ñal
    -0.45
    POSITIVE LOGITS
     transférez
    0.49
    AddTagHelper
    0.44
     informée
    0.39
    InteropServices
    0.37
     überweisen
    0.37
     CanadaChoose
    0.36
     AttributeSet
    0.36
    BufferException
    0.35
     Empieza
    0.33
    ArgsConstructor
    0.33
    Act Density 0.000%

    No Known Activations